© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58970
    Prev
    Next
    INDEX
    Explanations

    obesity and metabolic disease risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æijĦ
    -0.10
    æijĬ
    -0.10
    æĹłæĦı
    -0.08
    çĨŁæĤī
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
    è¡į
    -0.08
    æīĭèħķ
    -0.08
    竺
    -0.08
    hit
    -0.08
    è¿Ŀç«ł
    -0.08
    POSITIVE LOGITS
    åĮ¿
    0.10
     ske
    0.09
    æĻģ
    0.09
    è¶ħåĩº
    0.09
    ãĤŃãĥ³ãĤ°
    0.09
    åIJİæĤĶ
    0.09
    ÑĮÑı
    0.09
    åĽŀäºĭ
    0.09
    æľīéĻIJ
    0.09
    mgr
    0.09
    Activations Density 0.136%

    No Known Activations